Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.4757. Min Act: -0.1700
Data Index: 1045144 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.3820. Min Act: -0.1700
Data Index: 2280824 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.3507. Min Act: -0.1700
Data Index: 1069611 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.3195. Min Act: -0.1700
Data Index: 976478 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.1945. Min Act: -0.1700
Data Index: 4587209 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.2257. Min Act: -0.1700
Data Index: 619016 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.1945. Min Act: -0.1700
Data Index: 543775 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.1945. Min Act: -0.1700
Data Index: 4641081 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.1945. Min Act: -0.1700
Data Index: 4621397 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.1632. Min Act: -0.1700
Data Index: 7045003 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.1007. Min Act: -0.1700
Data Index: 1423499 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.0070. Min Act: -0.1700
Data Index: 5827651 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.0382. Min Act: -0.1700
Data Index: 8810605 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4757. Min Range: -6.4757
Max Act: 6.0070. Min Act: -0.1700
Data Index: 1529722 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4757. Min Range: -6.4757
Max Act: 5.9757. Min Act: -0.1700
Data Index: 633051 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4757. Min Range: -6.4757
Max Act: 5.9445. Min Act: -0.1700
Data Index: 5585812 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4757. Min Range: -6.4757
Max Act: 5.9132. Min Act: -0.1700
Data Index: 2538821 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4757. Min Range: -6.4757
Max Act: 5.9132. Min Act: -0.1700
Data Index: 6694136 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4757. Min Range: -6.4757
Max Act: 5.8820. Min Act: -0.1700
Data Index: 8215471 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4757. Min Range: -6.4757
Max Act: 5.8507. Min Act: -0.1700
Data Index: 5296258 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19